© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 39823
    Prev
    Next
    INDEX
    Explanations

    Madden

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CoreApplication
    -0.07
     enthusiasm
    -0.07
    Containing
    -0.07
    setData
    -0.07
    ,strong
    -0.07
    abcdefgh
    -0.07
    .toolStrip
    -0.06
    Ứ
    -0.06
     bookmark
    -0.06
    .hstack
    -0.06
    POSITIVE LOGITS
    раб
    0.08
     Project
    0.08
    ())->
    0.07
    bench
    0.07
     equation
    0.07
    idente
    0.07
     DBHelper
    0.07
    ↚
    0.06
    开元
    0.06
     mixin
    0.06
    Activations Density 0.003%

    No Known Activations